© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 20765
    Prev
    Next
    INDEX
    Explanations

    personal pronouns indicating the speaker or characters in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of personal pronouns and their associations in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quartered
    -0.77
    ĸļ
    -0.69
    ollen
    -0.68
    likely
    -0.66
     hitherto
    -0.65
    ktop
    -0.65
    nor
    -0.64
    beit
    -0.63
    INGTON
    -0.63
    Interstitial
    -0.62
    POSITIVE LOGITS
     recons
    1.01
     realized
    0.92
     realised
    0.92
     proceeded
    0.88
     piv
    0.84
     remembered
    0.82
     disappears
    0.79
     collapses
    0.78
     suddenly
    0.78
     explodes
    0.77
    Activations Density 0.179%

    No Known Activations